EdgeRank, the Facebook Newsfeed Algorithm

Michael Berstein, a researcher at MIT, posts a snapshot of the algorithm used to calculate what is shown to you in the Facebook Top News feed.

The algo is called EdgeRank and he describes it as such:

I’ll cut through the math using words. Whenever somebody interacts with a news feed item, they create an edge to that item. So if I comment on a friend’s new puppy photos, I’ve created an edge to your photos. When trying whether  to show the photos in your news feed, Facebook looks at how closely you interact with everyone who has an edge to the item. So, with the puppy photos, it considers your affinity to the friend who created the photos, and then me because I commented on them.

This all comes down to — initialization matters. If my high school friends are the first to comment on a news feed item, the EdgeRank of that item for other high school friends is high. So, other high school friends will see the item. If grad school friends are the first to comment, then other grad school friends are likewise going to see it.

I had no idea that the elapsed time between a posting and when you interact with the object had something to do with future relevance calculations but now that I think of it, it makes sense. The same has happened to my twitter usage – since I’ve shifted timezones, I mostly see tweets and posts from friends in the European timezone so, in a self-fulfilling way, any service looking to see which content I engage with the most will most likely determine that it’s things coming from my European friends.

More details about Faebook’s EdgeRank algorithm and a link to the full video which was presented at f8 over on TechCrunch.